© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113926
    Prev
    Next
    INDEX
    Explanations

    're / are followed by descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     managed
    -0.09
     Fir
    -0.09
     Glad
    -0.09
     lon
    -0.09
    aly
    -0.09
     SDK
    -0.08
     Lon
    -0.08
    fol
    -0.08
     bur
    -0.08
     Tud
    -0.08
    POSITIVE LOGITS
     welcome
    0.16
    welcome
    0.13
     supposed
    0.13
     right
    0.12
     Welcome
    0.11
     suppose
    0.11
     forgiven
    0.11
     aw
    0.10
     lucky
    0.10
     Impossible
    0.10
    Activations Density 0.019%

    No Known Activations